BI-RADS超声联合乳腺X线摄影分级诊断乳腺原位癌的临床应用价值

目的探讨BI-RADS超声联合乳腺X线摄影分级诊断乳腺原位癌的临床应用价值。方法对手术病理确诊的乳腺原位癌患者在术前均采用BI-RADS超声和乳腺X线摄影检查,比较两种检查方法单独及联合使用对乳腺原位癌的诊断检出率及诊断分级分类情况。结果 BI-RADS超声与乳腺X线摄影联合检查对乳腺原位癌的诊断符合率(96.88%)明显高于BI-RADS超声或乳腺X线摄影单独检查的检出率(87.50%、76.56%),且差异具有统计学意义。在超声分级诊断中,1级、2级、3级的误诊率分别为1.56%(1/64)、3.13%(2/64)、4.69%(3/64);在乳腺X线摄影分类诊断中,I类、II类、III类的误诊率分别为3.13%(2/64)、4.69%(3/64)、15.63%(10/64)。经统计学分析发现,在3级或Ⅲ类分级中,乳腺X线摄影检查的误诊率明显高于超声,且差异具有统计学意义。另外,超声在4级和5级诊断中敏感性分别为40.63%(26/64)、50.00%(32/64);乳腺X线摄影在IV类和V类诊断中敏感性分别为26.56%(17/64)、50.00%(32/64);经统计学分析发现,在4级或V类分级中,超声检查的敏感性明显高于乳腺X线摄影,且差异具有统计学意义。结论超声和乳腺X线摄影联合应用准确性更高,明显高于两者单独应用。     

乳腺良、恶性疾病:乳腺X线摄影、超声成像和组织病理学联系

目的：本研究目的是对经组织病理学证实患有乳腺疾病的男性患者，评价其乳腺X线摄影和超声成像的表现。材料与方法：对6年内获得的41例男性患者乳腺X线摄影和超声成像的资料，据BI-RADS分级法进行回顾性评价。结果：组织学上13例被诊断为癌，21例为男性乳房发育，3例为假性男性乳房发育，2例粉瘤及2例其它良性病变。乳腺X线摄影对鉴别良、恶性疾病，其敏感性、特异性、阳性预测值、阴性预测值和准确性分别为92%、89%、80%、96%和90%。辅以超声成像并不改变这些结果。然而超声成像对18.2%(2/11)的可疑病变能增加诊断的可信度。结论：本研…     

超声检查和乳腺X线摄影及数字乳腺断层摄影对乳腺肿块的应用

目的探讨超声检查、乳腺X线摄影和数字乳腺断层摄影对致密型乳腺无钙化肿块的诊断价值。方法收集100例致密型乳腺无钙化肿块患者的临床资料,以病理组织检查结果为金标准,进行乳腺影像报告和数据系统(BI-RADS)评价常规超声、乳腺X线摄影和数字乳腺断层摄影对疾病的检出率和符合率。结果 100例患者中,良性病变41例(41.00%),平均肿块直径(2.14±0.68)cm;恶性病变59例(59.00%),平均肿块直径(2.32±0.71)cm。良性病变与恶性病变患者肿块直径的比较,并无明显差异(P0.05)。超声对良性致密型乳腺无钙化肿块的检出率和符合率均明显高于乳腺X线摄影、数字乳腺断层摄影(P0.05),乳腺X线摄影与数字乳腺断层摄影对良性病变的检出率和符合率的比较,均无明显差异(P0.05)。三种影像学方法对恶性致密型乳腺无钙化肿块的检出率和符合率的比较,均无明显差异(P0.05)。超声对乳腺肿块良性病变的BI-RADS分类结果与乳腺X线摄影比较,存在明显差异(P0.05);超声与数字乳腺断层摄影、乳腺X线摄影与数字乳腺断层摄影对乳腺肿块良性病变的BI-RADS分类结果比较,并无明显差异(P0.05);三种影像学方法对乳腺肿块恶性病变的BI-RADS分类结果比较,并无明显差异(P0.05)。结论对致密型乳腺无钙化肿块数字乳腺断层摄影、超声的诊断价值相当,二者的检出率和诊断符合率均高于乳腺X线摄影。     

应用乳腺影像报告和数据系统分析乳腺叶状肿瘤的影像表现

目的 应用乳腺影像报告和数据系统(BI-RADS)探讨乳腺叶状肿瘤的X线、超声及MRI表现,以期提高对该病的影像诊断能力.方法 收集2004-2011年经手术病理证实的乳腺叶状肿瘤18例(20个病灶),其中良性6例,交界性5例,恶性7例.13例行乳腺X线摄影检查,13例做乳腺超声检查,4例行乳腺MRI检查.1例患者为单侧乳腺多发(3个)肿瘤,余17例为单发.按照BI-RADS术语,回顾性分析其影像表现及病变分类,并与大体及镜下病理表现对照.结果 无论良性、交界性还是恶性,影像表现为:除1例于X线摄影表现为局部致密及2例于超声表现为椭圆形,余肿块均为分叶状;边界清楚;＜5 cm肿块除1例回声不均匀,余回声(或信号)均匀,而＞5 cm者因囊变易回声(或信号)不均匀;血供丰富;未见钙化;未侵犯乳头及皮肤;未见腋窝淋巴结转移.交界性及恶性者MRI动态增强曲线为III型,扩散加权成像表现为高信号,波谱见胆碱峰.BI-RADS病变分类多为4类.结论 应用BI-RADS有利于乳腺叶状肿瘤影像结果的综合比较.     

男性乳腺肿块的乳腺X线分析及其临床意义

目的:研究引起男性乳腺肿块常见疾病的X线表现特点及诊断,以提高对其认识.方法:收集因乳腺肿块进行乳腺X线检查的男性49例,回顾性分析上述患者的乳腺X线表现及临床特点,归纳可引起男性乳腺肿块的常见疾病种类.结果:49例男性患者,经乳腺X线检查诊断为男性乳腺发育症45例,其中结节型31例(68.9％),树枝型6例(13.3％),弥漫型8例(17.8％).另外4例经X线检查发现乳腺肿块归为BI-RADS 4类,最终手术病理证实为浸润性乳腺癌1例,转移性腺癌1例,囊内乳头状癌1例,脂肪坏死1例.结论:男性乳腺发育症和男性乳腺癌是引起男性乳腺肿块的常见病因,前者一般通过典型X线表现就可做出正确诊断,男性乳腺癌、脂肪坏死等少见疾病的确诊仍有赖于最终病理诊断.     

乳腺X线摄影与超声检查对乳腺黏液腺癌诊断价值的比较

目的 探讨X线摄影与超声检查对乳腺黏液腺癌的诊断价值.方法 回顾性收集本院先后行术前X线检查和超声检查,手术治疗并经病理学证实的黏液腺癌22例患者.结果 22例病例中,15例为单纯型黏液腺癌,7例为混合型黏液腺癌;乳腺X线诊断为癌灶者共13例,诊断正确率59.09%,超声诊断癌灶者20例,诊断准确率为90.90%,明显高于X线(P=0.039).结论 乳腺黏液腺癌在乳腺X线及超声影像上有一定特征性表现,但由于其病理学特性的限制,乳腺X线对其诊断的准确性低于超声检查.     

BI-RADS系统在乳腺X线摄影及超声诊断中的应用

目的:探讨BI-BADS分类系统在乳腺X线及超声诊断中的价值。方法:搜集2007年12月-2008年12月均行X线及超声检查、有病理证实或临床随诊1年以上者共1432例患者。年龄23～83岁,均值49.5岁。绝经565例(39.5%),未绝经867例(60.5%)。根据BI-RADS系统对两种检查的结果进行评价。结果:共检出1500个病灶,737个(49.1%)良性病灶,763个(50.9%)恶性病灶。X线BI-RADS 1至5类的恶性百分比分别为12.9%、3.1%、8.9%、70.9%和98.3%;超声分别为3.9%、3.9%、6.3%、62.8%和95.7%。X线、超声BI-RADS分类ROC曲线下的面积分别为0.901和0.945(P=0.000)。X线摄影及超声检查的敏感度分别为90.0%和95.4%,特异度为83.0%和84.8%,准确度为86.6%及90.2%。结论:X线及超声BI-RADS分类系统能很好预测乳腺恶性肿瘤的风险,对于临床有指导价值。     

手持式全乳腺超声在BI-RADS评级评价乳腺摄影阴性的女性致密乳腺的表现

目的用BI-RADS评级评价乳腺摄影阴性的女性致密乳腺超声表现。材料与方法本研究回顾性分析了3820次致密乳腺乳腺摄影阴性后行手持式双侧全乳腺的超声检     

X线乳腺摄影与超声检查对乳腺黏液腺癌的诊断比较

目的：比较X线乳腺摄影与超声检查在乳腺黏液腺癌诊断中的临床应用。方法对乳腺黏液腺癌患者行X线乳腺摄影检查及乳腺超声检查,进行分析比较。结果72例乳腺粘液癌患者中包括42例单纯型乳腺粘液癌和30例混合型乳腺粘液癌,并且不同类型乳腺粘液癌其形态学特点并不相同;根据BI‐RADS标准诊断标准,X线乳腺摄影检查43例与病情相符,符合率为59．7﹪;而超声检查符合例数为64例符合率为83．3﹪,二者相比,差异具有统计学意义, P＜0．05。结论对于乳腺粘液癌超声检查诊断正确性高于X线乳腺摄影检查。     

全数字化乳腺X线摄影与传统乳腺X线摄影对比分析

目的:探讨全数字化乳腺X线摄影(FFDM)与传统乳腺X线摄影(SFM)的临床应用效果.方法:回顾分析使用传统乳腺X线机及使用全数字化乳腺机摄影各800例的影像及临床资料,分别统计两组病例的平均曝光次数、平均检查时间,同时对乳房各部分细微结构显示率进行评价,并将两组病例中经手术病理证实为乳腺癌病例的病理结果与术前X线诊断作对照.结果:SFM组平均曝光次数5.12次/人,平均检查时间20分钟/人;FFDM组平均曝光次数4.22次/人,平均检查时间6.3分钟/人.同时清晰显示乳房各部分微细结构显示率为SFM组284例(35.5%);FFDM组791例(98.9%).SFM与FFDM诊断乳腺癌的敏感度、特异度、准确度分别为80.2%时87.5%;79.8%对85.2%;81.3%对88.5%.结论:与传统乳腺X线摄影对比,全数字化乳腺X线摄影操作简单,成像快捷,图像质量好,在乳腺癌(尤其是早期乳癌)诊断方面优于传统乳腺X线摄影.     

乳腺影像报告和数据系统在国人女性乳腺癌筛查中的应用价值

目的 探讨乳腺影像报告和数据系统(BI-RADS)评估分类在国人女性乳腺癌筛查中的应用价值.方法 搜集2009年8月至12月参加乳腺癌筛查项目中行乳腺X线摄影的3483名妇女资料,参照BI-RADS标准对乳腺评估分类,对于疾病的诊断最终以组织病理结果为金标准,计算BI-RADS评估分类的准确度、敏感度、特异度及BI-RADS各类的阳性预测值(PPV)和阴性预测值(NPV).结果 3483名受检妇女乳腺组成中脂肪型、散在腺体型、不均匀致密型和高度致密型分别有267、1245、1890和81名.进行BI-RADS评估分类,0～5类分别为273(7.8%)、1011(29.0%)、1741(50.0%)、383(11.0%)、59(1.7%)和16(0.5%)名.71例受检者的77个乳腺病变经病理证实,包括恶性病变29例,良性病变48例.BI-RADS评估分类的准确度为63.6%(49/77),敏感度为93.1%(27/29),特异度为45.8%(22/48),BI-RADS总体PPV为50.9%(27/53),0类、4类和5类的PPV分别为25.0%(1/4)、36.4%(12/33)和87.5%(14/16),2类、3类的NPV分别为90.9%(10/11)和100.0%(12/12).结论 乳腺X线摄影应用BI-RADS评估分类可以有效地预测乳腺恶性病变,在国人女性乳腺癌筛查应用中有一定价值.     

乳腺影像报告和数据系统在国人女性乳腺癌筛查中的应用价值

目的 探讨乳腺影像报告和数据系统(BI-RADS)评估分类在国人女性乳腺癌筛查中的应用价值.方法 搜集2009年8月至12月参加乳腺癌筛查项目中行乳腺X线摄影的3483名妇女资料,参照BI-RADS标准对乳腺评估分类,对于疾病的诊断最终以组织病理结果为金标准,计算BI-RADS评估分类的准确度、敏感度、特异度及BI-RADS各类的阳性预测值(PPV)和阴性预测值(NPV).结果 3483名受检妇女乳腺组成中脂肪型、散在腺体型、不均匀致密型和高度致密型分别有267、1245、1890和81名.进行BI-RADS评估分类,0～5类分别为273(7.8%)、1011(29.0%)、1741(50.0%)、383(11.0%)、59(1.7%)和16(0.5%)名.71例受检者的77个乳腺病变经病理证实,包括恶性病变29例,良性病变48例.BI-RADS评估分类的准确度为63.6%(49/77),敏感度为93.1%(27/29),特异度为45.8%(22/48),BI-RADS总体PPV为50.9%(27/53),0类、4类和5类的PPV分别为25.0%(1/4)、36.4%(12/33)和87.5%(14/16),2类、3类的NPV分别为90.9%(10/11)和100.0%(12/12).结论 乳腺X线摄影应用BI-RADS评估分类可以有效地预测乳腺恶性病变,在国人女性乳腺癌筛查应用中有一定价值.

Abstract：

Objective To study the value of breast imaging reporting and data system (BI-RADS)in Chinese breast cancer screening. Methods A total number of 3483 women participated in breast cancer screening with mammography in Hexi district in Tianjin from August to December 2009, which was organized by ministry of public health. BI-RADS assessment categories and recommendations were compared with histological findings. The precision, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were calculated. Results Among 3483 screening mammography cases, 267 were almost entirely fat breast, 1245 were scauered fibroglandular, 1890 were dense and 81 extremely dense.There were 1011 patients(29.0%) with category 1, 1741 (50.0%) with category 2, 383 (11.0%) with category 3, 59 patients(1. 7%) with category 4 and 16 (0. 5%) with category 5 according to BI-RADS assessment categories. Totally, 71 women with 77 lesions were confirmed by histological examinations. There were 29 malignant and 48 benign lesions. The diagnostic precision, sensitivity, specificity of BI-RADS were 63. 6% (49/77) , 93. 1% (27/29) and 45.8% (22/48) . The general PPV of BI-RADS was 50. 9%(27/53). The PPV of categories 0, 4, 5 were 25.0% (1/4), 36. 4% (12/33) and 87. 5% (14/16). The NPV of categories 2 and3 were90.9% (10/11), 100.0% (12/12). Conclusions B1-RADS is of much value in assessing the breast malignancy. It is applicable in Chinese breast cancer screening.     

乳腺影像报告和数据系统在国人女性乳腺癌筛查中的应用价值

目的 探讨乳腺影像报告和数据系统(BI-RADS)评估分类在国人女性乳腺癌筛查中的应用价值.方法 搜集2009年8月至12月参加乳腺癌筛查项目中行乳腺X线摄影的3483名妇女资料,参照BI-RADS标准对乳腺评估分类,对于疾病的诊断最终以组织病理结果为金标准,计算BI-RADS评估分类的准确度、敏感度、特异度及BI-RADS各类的阳性预测值(PPV)和阴性预测值(NPV).结果 3483名受检妇女乳腺组成中脂肪型、散在腺体型、不均匀致密型和高度致密型分别有267、1245、1890和81名.进行BI-RADS评估分类,0～5类分别为273(7.8%)、1011(29.0%)、1741(50.0%)、383(11.0%)、59(1.7%)和16(0.5%)名.71例受检者的77个乳腺病变经病理证实,包括恶性病变29例,良性病变48例.BI-RADS评估分类的准确度为63.6%(49/77),敏感度为93.1%(27/29),特异度为45.8%(22/48),BI-RADS总体PPV为50.9%(27/53),0类、4类和5类的PPV分别为25.0%(1/4)、36.4%(12/33)和87.5%(14/16),2类、3类的NPV分别为90.9%(10/11)和100.0%(12/12).结论 乳腺X线摄影应用BI-RADS评估分类可以有效地预测乳腺恶性病变,在国人女性乳腺癌筛查应用中有一定价值.     

The positive predictive value of the breast imaging reporting and data system (BI-RADS) as a method of quality assessment in breast imaging in a hospital population

Evaluation of the diagnostic performance of mammography and US in our hospital, based upon the positive predictive value (PPV) for breast cancer of the breast imaging reporting and data system (BI-RADS) final assessment categories, has been performed. A follow-up study of 2,762 mammograms was performed, along with 955 diagnostic exams and 1,807 screening exams. Additional US was performed in 655 patients (23.7%). The combined reports were assigned a BI-RADS category. Follow-up was obtained by pathologic examination, mammography at 12 months or from PALGA, a nationwide network and registry of histo- and cytopathology. Overall sensitivity was 85% (specificity 98.7%); sensitivity of the diagnostic examinations was 92.9% (specificity 97.7%) and of the screening examinations 69.2% (specificity 99.2%). The PPV of BI-RADS 1 was 5 of 1,542 (0.3%), and of BI-RADS 2, it was 6 of 935 (0.6%). BI-RADS 3 was 6 of 154 (3.9%), BI-RADS 4 was 39 of 74 (52.7%) and BI-RADS 5 was 57 of 57 (100%). The difference between BI-RADS 1 and 2 vs. BI-RADS 3 was statistically significant (P<0.01). Analysis of BI-RADS 3 cases revealed inconsistencies in its assignment. Evaluation of the BI-RADS final assessment categories enables a valid analysis of the diagnostic performance of mammography and US and reveals tools to improve future outcomes.     

结合MRI和X线分类对乳腺X线筛查为BI-RADS 4类肿块的处理体会

目的:评价结合MRI和X线分类对乳腺X线筛查为BI-RADS 4类肿块的良恶性评估价值,探讨BI-RADS 4类肿块新的处理建议.方法:X线筛查为BI-RADS 4a类(105个)、4b类(42个)和4c类(19个)的151例共166个乳腺肿块,在活检前行MRI.动态增强结合扩散加权成像(DWI)进行MRI BI-RADS分类.结合X线与MRI分类提出新的良恶性评估法.统计X线与MRI诊断乳腺癌的敏感度、特异度及诊断符合率;绘制两者的ROC曲线,Z检验比较曲线下面积;统计结合MRI和X线的新的良恶性评估法发现乳腺癌的敏感性、诊断符合率和对良性病变检出率.结果:2名X线诊断医师和2名MRI诊断医师的BI-RADS分类的Kappa值分别为0.70和0.76,一致性较好.166个肿块,恶性41个,占24.7％.X线BI-RADS 4a类105个:恶性12个,MRI分类为4、5类12个;良性93个,MRI为2、3类81个.X线BI-RADS 4b类42个:恶性16个,MRI分类为4、5类15个;良性26个,MRI为2、3类16个.X线BI-RADS 4c类19个:恶性13个,MRI分类为4、5类12个;良性6个,MRI为3类2个.X线诊断敏感度、特异度为70.7％、74.4％,诊断符合率为73.5％.MRI诊断敏感度、特异性及诊断符合率为95.1％、79.2％和83.1％.X线及MRI诊断乳腺癌的ROC曲线下面积分别为0.749及0.927,两者差异有统计学意义(Z=2.282,P＜0.05).新的良恶性评估法发现乳腺癌的敏感度为100％,诊断符合率为77.7％,良性病变检出率为53.0％.结论:MRI对乳腺X线筛查为BI-RADS 4类肿块有较高的诊断价值.结合X线及MRI分类进行新的良恶性评估,能减少良性肿块不必要的活检.     

The negative predictive value of electrical impedance scanning in BI-RADS category IV breast lesions

OBJECTIVES: We sought to prospectively assess the value of electrical impedance scanning (EIS) in discriminating benign from malignant lesions classified as BI-RADS category IV in mammography in comparison with ultrasound (US), with a special focus on negative prediction. MATERIALS AND METHODS: EIS was performed on 128 BI-RADS category IV lesions in 121 women (mean, 51.8 years). The newly developed EIS software 2.67 calculates a BI-RADS-like level of suspicion (LOS) on a 5-grade scale. LOS 1, 2, and 3 were considered negative; LOS 4 and 5 were considered positive. Histopathologic results were obtained in all lesions. RESULTS: Histology proved 37 lesions malignant, 91 benign. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of EIS compared with US were 94.6%, 74.7%, 80.5%, 60.3%, 97.1% versus 90.5%, 33.8%, 47.2%, 29.7%, 92.0%, respectively. In 43 lesions sized < or = 10 mm, EIS demonstrated better sensitivity, specificity, accuracy, PPV, and NPV of 100%, 83.3%, 90.7%, 82.6%, and 100%, respectively. Although NPV was also high, US showed no sufficient results in 39 (30.5%) lesions because of microcalcifications. Receiver operating curve analysis revealed best results for a combined use of US and EIS. CONCLUSIONS: With a NPV of 97.1% of EIS in BI-RADS category IV breast lesions, a negative result in these lesions could be firm indication to manage them as BI-RADS-category III and refer patients for a 6-month short-interval follow-up rather than performing a biopsy. The best adjunctive diagnostic performance can be achieved by a combination of US and EIS. Costs and patient morbidity could be minimized.     

Contrast-enhanced MR mammography for evaluation of the contralateral breast in patients with diagnosed unilateral breast cancer or high-risk lesions

PURPOSE: To prospectively evaluate accuracy of gadobenate dimeglumine-enhanced magnetic resonance (MR) mammography for depiction of synchronous contralateral breast cancer in patients with newly diagnosed unilateral breast cancer or high-risk lesions, with histologic analysis or follow-up as reference. MATERIALS AND METHODS: The study had ethics committee approval; all patients provided written informed consent. One hundred eighteen consecutive women (mean age, 52 years) with unilateral breast cancer or high-risk lesions and negative findings in the contralateral breast at physical examination, ultrasonography, and conventional mammography underwent gadobenate dimeglumine-enhanced 1.5-T MR mammography. Transverse three-dimensional T1-weighted gradient-echo images were acquired before and at 0, 2, 4, 6, and 8 minutes after gadobenate dimeglumine administration (0.1 mmol per kilogram body weight). Breast Imaging Reporting and Data System (BI-RADS) was used to categorize breast density and the level of suspicion for malignant contralateral breast lesions. Results were compared with histologic findings. Sensitivity, specificity, accuracy, and positive and negative predictive values for contrast-enhanced MR mammography were evaluated. RESULTS: Contrast-enhanced MR mammography revealed contralateral lesions in 28 (24%) of 118 patients. Twenty-four lesions were detected in patients with dense breasts (BI-RADS breast density category III or IV). Lesions in eight (29%) of 28 patients were BI-RADS category 4; patients underwent biopsy. Lesions in 20 (71%) patients were BI-RADS category 5; patients underwent surgery. At histologic analysis, 22 lesions were confirmed as malignant; six lesions were fibroadenomas. No false-negative lesions were detected; none of the fibroadenomas were BI-RADS category 5. The sensitivity, specificity, accuracy, and positive and negative predictive values of contrast-enhanced MR mammography for depiction of malignant or high-risk contralateral lesions were 100%, 94%, 95%, 79%, and 100%, respectively. Follow-up findings (12-24 months) confirmed absence of contralateral lesions in 90 of 118 patients with negative contrast-enhanced MR mammographic findings in the contralateral breast. CONCLUSION: Contrast-enhanced MR mammography is accurate for detection of synchronous contralateral cancer or high-risk lesions in patients with newly diagnosed breast cancer or high-risk lesions.     

MR imaging in probably benign lesions (BI-RADS category 3) of the breast

PURPOSE: To investigate the role of dynamic magnetic resonance (MR) imaging in the evaluation of probably benign lesions (BI-RADS category 3) and its contribution to patient management. MATERIALS AND METHODS: Dynamic breast MR imaging was performed in 56 lesions assessed as probably benign in mammography of 43 patients. In MR imaging, T2-weighted turbo spin echo (TSE) with fat suppression sequence followed by pre- and post-contrast T1-weighted 3D-FLASH sequences were used. MR imaging findings were scored using 0-2 point criterion scale. The lesions were divided into five groups according to their total score (0 point: group 1, negative; 1-2 points: group 2, benign; 3 points: group 3, probably benign; 4-5 points: group 4, suspicious for malignancy; 6-8 points: group 5, highly suggestive of malignancy). Histopathologic verification of lesions in group 4 and above was obtained. Lesions in group 3 were either biopsied or followed up by mammography or MR imaging. Lesions in group 1-2 were followed by mammography of 6-month intervals for 2 years. The sensitivity, specificity, accuracy, and positive and negative predictive values of MR imaging in the determination of malignancy in BI-RADS category 3 lesions were calculated. RESULTS: Fifty-six findings (45 mass, 9 breast tissue, 2 focal enhancement) in 43 patients were detected in MR imaging. According to their total score, 41 lesions (73.2%) and breast tissue had 0 point (group 1); 10 lesions (17.8%) had 1-2 points (group 2); 2 lesions (3.6%) had 3 points (group 3); 2 lesions (3.6%) had 4 and 5 points (group 4); and 1 lesion (1.8%) had 6 points (group 5). Ten lesions (of six in groups 1 and 2, one in group 3, three in groups 4 and 5) were histopathologically confirmed. Out of 10 lesions, only 1 (1.8%) with 4 points in group 4 was diagnosed as invasive ductal carcinoma. Other lesions followed with mammography or MR imaging did not change. The sensitivity, specificity, accuracy, positive and negative predictive values of MR imaging in the determination of malignancy in BI-RADS category 3 lesions were calculated as 100, 96.4, 96.4, 33.3, and 100%, respectively. CONCLUSION: In the evaluation of BI-RADS category 3 lesions, dynamic MR imaging does not provide additional information with low positive predictive value similar to that of short interval mammography follow-up.     

Characterization of breast lesions with CE-MR multimodal morphological and kinetic analysis: comparison with conventional mammography and high-resolution ultrasound

Objective

Evaluation of the diagnostic value of magnetic resonance mammography and comparison with conventional mammography and ultrasonography in cases of women with suspicious breast lesions.

Subjects and methods

Sixty-nine women (age range 39–68 years) with 78 focal breast lesions were examined with mammography, ultrasonography and dynamic magnetic resonance mammography. The lesions were classified according to the Breast Imaging Reporting and Data System (BI-RADS) lexicon of the American College of Radiology for each diagnostic method. Histological reports were available after biopsy or surgical excision of the lesions.

Results

Pathological examination confirmed that 53 lesions were malignant and 25 benign. Conventional mammography estimated a total of 59/78 lesions as malignant with 44 true positive lesions, ultrasonography estimated a total of 50/78 lesions as malignant with 44 true positive lesions and magnetic resonance mammography estimated a total of 66/78 lesions as malignant with 52 true positive lesions. Sensitivity and specificity of magnetic resonance mammography in the diagnosis of malignancy was 98.1% and 44%, of conventional mammography 83% and 40% and of ultrasonography 83% and 76%. Negative predictive value for magnetic resonance mammography was 91.7%, for ultrasonography 67.9% and for mammography 52.6% for malignancies.

Conclusion

Magnetic resonance mammography has the highest negative predictive value compared with mammography and ultrasound in cases of suspicious breast lesions. The combination of morphologic and enhancement criteria can improve the diagnostic capability of magnetic resonance mammography (MRM) in breast lesion characterization.     

Application of deep learning to establish a diagnostic model of breast lesions using two-dimensional grayscale ultrasound imaging

PurposeThere are currently few specific artificial intelligence (AI) studies for Breast Imaging Reporting and Data System (BI-RADS) category 4A lesions. This study aimed to establish an AI diagnostic model of breast lesions using two-dimensional grayscale ultrasound imaging and to compare its performance with that of radiologists.MethodsThe ultrasound images of 1311 lesions were evaluated by radiologists according to the BI-RADS categories, using pathology results as reference. Two classification standards (standards 1 and 2) for benign and malignant lesions were defined and used to calculate the diagnostic performance of radiologists, altogether and individually. The breast lesion images were also used to develop an AI diagnostic model.ResultsThe diagnostic performance of AI and that of the radiologists were compared using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV). All parameters of diagnostic performance, except for sensitivity and NPV, improved with standard 2. For the 202 lesions in the test set, the diagnostic performance of the AI model had 77.0% accuracy, 82.0% sensitivity, 71.7% specificity, 79.3% PPV, 75.1% NPV, and an AUC of 0.846. When the AI model was used to analyze category 4A lesions, the PPV was 9.3%, which was better than that of the radiologists, although not significantly.ConclusionsDeep learning technology shows a good performance in classifying benign and malignant breast lesions. It may be potentially used in practice to improve diagnostic accuracy and reduce unnecessary biopsies of breast lesions.